Many bioinformatics programming tasks can be automated with ChatGPT

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Piccolo, Stephen R., Denny, Paul, Luxton-Reilly, Andrew, Payne, Samuel, Ridge, Perry G.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929195279450112
author Piccolo, Stephen R.
Denny, Paul
Luxton-Reilly, Andrew
Payne, Samuel
Ridge, Perry G.
author_facet Piccolo, Stephen R.
Denny, Paul
Luxton-Reilly, Andrew
Payne, Samuel
Ridge, Perry G.
contents Computer programming is a fundamental tool for life scientists, allowing them to carry out many essential research tasks. However, despite a variety of educational efforts, learning to write code can be a challenging endeavor for both researchers and students in life science disciplines. Recent advances in artificial intelligence have made it possible to translate human-language prompts to functional code, raising questions about whether these technologies can aid (or replace) life scientists' efforts to write code. Using 184 programming exercises from an introductory-bioinformatics course, we evaluated the extent to which one such model -- OpenAI's ChatGPT -- can successfully complete basic- to moderate-level programming tasks. On its first attempt, ChatGPT solved 139 (75.5%) of the exercises. For the remaining exercises, we provided natural-language feedback to the model, prompting it to try different approaches. Within 7 or fewer attempts, ChatGPT solved 179 (97.3%) of the exercises. These findings have important implications for life-sciences research and education. For many programming tasks, researchers no longer need to write code from scratch. Instead, machine-learning models may produce usable solutions. Instructors may need to adapt their pedagogical approaches and assessment techniques to account for these new capabilities that are available to the general public.
format Preprint
id arxiv_https___arxiv_org_abs_2303_13528
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Many bioinformatics programming tasks can be automated with ChatGPT
Piccolo, Stephen R.
Denny, Paul
Luxton-Reilly, Andrew
Payne, Samuel
Ridge, Perry G.
Other Quantitative Biology
Computers and Society
Computer programming is a fundamental tool for life scientists, allowing them to carry out many essential research tasks. However, despite a variety of educational efforts, learning to write code can be a challenging endeavor for both researchers and students in life science disciplines. Recent advances in artificial intelligence have made it possible to translate human-language prompts to functional code, raising questions about whether these technologies can aid (or replace) life scientists' efforts to write code. Using 184 programming exercises from an introductory-bioinformatics course, we evaluated the extent to which one such model -- OpenAI's ChatGPT -- can successfully complete basic- to moderate-level programming tasks. On its first attempt, ChatGPT solved 139 (75.5%) of the exercises. For the remaining exercises, we provided natural-language feedback to the model, prompting it to try different approaches. Within 7 or fewer attempts, ChatGPT solved 179 (97.3%) of the exercises. These findings have important implications for life-sciences research and education. For many programming tasks, researchers no longer need to write code from scratch. Instead, machine-learning models may produce usable solutions. Instructors may need to adapt their pedagogical approaches and assessment techniques to account for these new capabilities that are available to the general public.
title Many bioinformatics programming tasks can be automated with ChatGPT
topic Other Quantitative Biology
Computers and Society
url https://arxiv.org/abs/2303.13528